Atlas

Benchmarks

← All benchmarks

Arena Text — Medicine & Healthcare (No Style Control)

Professional Work

Raw Arena rating for medicine and healthcare industry prompts without style-control adjustment. Higher ratings indicate stronger preference in blind pairwise user votes.

Top models (higher is better)

ModelScore
Gemini 4 Argon1537
Claude Fable 5.11533
Claude Opus 51526
Claude Opus 5.51512
Muse Wonder1510
Gemini 3.8 Flash1506
Opus 4.61504
Qwen3.8-Max1503
MiMo-V2.6-Pro1496
Opus 4.71496
Muse Spark 1.21495
Gemini 3.7 Flash1495
Muse Spark 1.31493
Gemini 3 Pro Preview1492
Kimi K31488
ERNIE 5.11487
Gemini 3.1 Pro Preview1487
Gemini 3.5 Flash1484
DeepSeek V4.1 Flash1483
GLM-5.31482
Muse Spark 1.11480
Claude Fable 51480
Qwen3.7 Max Preview1479
Gemini 2.5 Pro1476
Muse Spark1476
GLM-5.3 Flash1475
GLM-5.21475
GLM-5.11473
MiMo-V2.5-Pro1472
GLM-4.71469
DeepSeek-V3.2-Exp1469
Gemini 3.6 Flash1469
DeepSeek-V3.1-Terminus1468
Qwen3 Max Preview1468
Claude Sonnet 5.51467
DeepSeek-V4-Pro1465
GPT-5.51465
Qwen3.7-Plus (source unspecified)1465
Opus 4.81464
Gemini 3 Flash Preview1462
Loading Atlas data…